Needle breakage detection method, apparatus, storage medium, and program product for a glove machine

Abstract

The application provides a glove machine needle breakage detection method, device, storage medium and program product, comprising: acquiring multiple frames of detection images when the glove machine is working; for each frame of detection image, matching a preset jitter correction template with the detection image to obtain an initial positioning position of at least one target needle tip located at a middle position of a needle array; matching the positioning position of each needle tip with the initial positioning position of the at least one target needle tip to determine the position of each needle tip in the detection image; performing image recognition based on the position of each needle tip to determine a needle breakage detection result of each frame of detection image; and generating a final needle breakage detection result according to the needle breakage detection result of each frame of detection image. In the application, multiple frames of detection images are acquired by a shooting unit, two positioning steps and twice flaw image recognition are performed to solve the problems of machine jitter and false detection and missed detection, improve the detection accuracy, and realize multi-frame visual automatic and accurate detection of glove machine needle breakage flaws.

Description

Technical Field

[0008] ,

[0007] ,

[0011] ,

[0010] ,

[0009] , , , ,

[0001] This application relates to the technical field of glove machines, and particularly to a method, device, storage medium, and program product for detecting broken needles of a glove machine. Background Art

[0002] With the development of science and technology, traditional factories are transitioning towards big data and industrial Internet of Things, and unmanned factories have become a trend. How to transform traditional glove machine factories into unmanned factories has always been a problem we are committed to solving.

[0003] In existing glove machine factories, quality inspection is the most labor-intensive process. How to achieve unmanned quality inspection, improve the yield rate, and reduce defective products are the pain points we need to solve. For the faults of broken yarn and broken elastic thread during the operation of the glove machine, automated detection can be achieved, but currently, automated detection of broken needles of the glove machine cannot be achieved. Summary of the Invention

[0004] This application provides a method, device, storage medium, and program product for detecting broken needles of a glove machine to solve the problem in the prior art that automated detection of broken needles of a glove machine cannot be achieved.

[0005] An embodiment of this application provides a method for detecting broken needles of a glove machine. The glove machine is equipped with a knitting needle structure, and the knitting needle structure includes a knitting needle array. The method includes:

[0006] Obtain multiple frames of detection images during the operation of the glove machine, where the detection images include the knitting needle structure area;

[0007] For each frame of the detection image, match a preset jitter correction template with the detection image to obtain the initial positioning positions of at least one target needle tip located at the middle position of the knitting needle array;

[0008] For each frame of the detection image, match the calibration positions of each needle tip with the initial positioning positions of at least one target needle tip to determine the positions of each needle tip in the detection image;

[0009] Based on the positions of each needle tip, perform image recognition to determine the broken needle detection result of each frame of the detection image; generate the final broken needle detection result according to the broken needle detection results of each frame of the detection image. <00​​​​

[0012] The second central region of the needle array in the detection image is determined based on the relative relationship between the jitter correction region and the first central region in the jitter correction template, and the first reference region.

[0013] The second central region is used for needle tip image recognition to determine the initial positioning position of at least one target needle tip.

[0014] In one embodiment, for each frame of the detection image, the calibrated position of each needle tip is matched with the initial positioning position of at least one target needle tip to determine the position of each needle tip in the detection image, specifically including:

[0015] A reference needle tip is selected from at least one target needle tip based on the initial positioning position of at least one target needle tip, and the initial positioning position of the reference needle tip is determined.

[0016] Match the initial positioning position of the reference needle tip with the calibrated position of each needle tip to determine the offset between the initial positioning position and the calibrated position of the reference needle tip.

[0017] The calibration positions of each needle tip are offset as a whole based on the offset amount to obtain the position of each needle tip in the detection image.

[0018] In one embodiment, image recognition is performed based on the position of each needle tip to determine the broken needle detection result for each frame of the detection image, specifically including:

[0019] For each frame of the detection image, the detection area of ​​each needle tip is determined according to the position of each needle tip, and image recognition is performed on the detection area of ​​each needle tip to determine the broken needle detection result of each needle tip.

[0020] If the needle breakage detection results for each needle tip indicate no broken needles, then the needle breakage detection result for the detection image is determined to be no broken needles.

[0021] In one embodiment, determining the broken needle detection result for each frame of the detection image based on the position of each needle tip further includes:

[0022] If the needle breakage detection result of at least one needle tip is a broken needle, then the needle tip with the broken needle detection result is marked as a suspicious needle tip;

[0023] For each suspicious needle tip, the suspicious area is determined based on the position of the needle tips adjacent to the suspicious needle tip, and image recognition is performed on the suspicious area;

[0024] If the identification result of each suspicious area is no broken needle, then the broken needle detection result of the detection image is determined to be no broken needle;

[0025] If the identification result of at least one suspicious area is that there is a broken needle, then the broken needle detection result of the detection image is determined to be that there is a broken needle, and the broken needle location is stored.

[0026] In one embodiment, acquiring multiple frames of detection images during the operation of the glove machine specifically includes:

[0027] When it is determined that the operating head is directly above the needle array, a first movement command is generated. The first movement command is used to control the operating head to move to one side of the needle array.

[0028] Generate a first shooting command, wherein the first shooting command controls the camera to capture the first frame of the glove machine's detection image;

[0029] A second movement command is generated, which controls the operating head to move to the other side of the needle array;

[0030] Generate a second shooting command, wherein the second shooting command controls the camera to capture a second frame of the glove machine's detection image;

[0031] or

[0032] When it is determined that the operating head is located on one side of the needle array, a first shooting command is generated, which controls the camera to capture the first frame of the glove machine's detection image;

[0033] Generate a second movement command, the first movement command being used to control the operating head to move to the other side of the needle array;

[0034] A second shooting command is generated, wherein the second shooting command controls the camera to capture a second frame of the glove machine's detection image.

[0035] In one embodiment, generating the final broken needle detection result based on the broken needle detection result of each frame of the detection image specifically includes:

[0036] When both the final broken needle detection result of the first frame detection image and the final broken needle detection result of the second frame detection image show broken needles, determine whether the broken needle position of the first frame detection image and the broken needle position of the second frame detection image are the same.

[0037] If at least one broken needle is in the same location, the knitting needle structure is determined to have a broken needle; if all broken needles are in different locations, the knitting needle structure is determined not to have a broken needle.

[0038] Another embodiment of this application provides a detection device, including: a processor, and a memory communicatively connected to the processor;

[0039] The memory stores the instructions that the computer executes;

[0040] The processor executes computer execution instructions stored in memory to implement the methods described in the above embodiments.

[0041] Another embodiment of this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods described in the above embodiments.

[0042] Another embodiment of this application provides a computer program product, including a computer program that, when executed by a processor, implements the methods described in the above embodiments.

[0043] The broken needle detection method, equipment, storage medium, and program product for glove machines provided in this application acquire multiple frames of detection images from the glove machine, and perform initial pixel matching between the jitter correction template and the detection images. A secondary positioning matching is then performed between the calibrated position of each needle tip and the initial positioning position of at least one target needle tip. This two-step positioning determines the position of each needle tip in the detection image, improving accuracy. Image recognition is then performed based on the position of each needle tip to determine the broken needle detection result for each frame of the detection image, solving the problems of unavoidable machine jitter and missed / false detections. The broken needle detection results from each frame of the detection image are fused to generate the final broken needle detection result, determining the broken needle detection result of the glove machine. This achieves two-stage defect judgment, solves the problem of false alarms in the system, improves the accuracy of the broken needle detection result, and realizes a multi-frame visual automated and accurate detection effect for broken needle defects in glove machines. Attached Figure Description

[0044] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0045] Figure 1 This application provides a structural diagram of a broken needle detection system for a glove machine according to an embodiment of the present application.

[0046] Figure 2 A flowchart of a broken needle detection method for a glove machine is provided in another embodiment of this application;

[0047] Figure 3 This is a schematic diagram of preliminary localization of a single-frame detection image provided in another embodiment of this application;

[0048] Figure 4 A flowchart of a method for determining the broken needle detection result of each frame of detection image based on the position of each needle tip, as provided in another embodiment of this application;

[0049] Figure 5 A flowchart of a broken needle detection method for a glove machine is provided in another embodiment of this application;

[0050] Figure 6 This is a flowchart of a method for obtaining two frames of detection images of a glove machine in operation, provided in another embodiment of this application.

[0051] Figure 7 Schematic structural diagram of the broken needle detection device for the glove machine provided in another embodiment of the present application;

[0052] Figure 8 Schematic structural diagram of a detection device provided in another embodiment of the present application.

[0053] Through the above-mentioned drawings, specific embodiments of the present application have been shown, and more detailed descriptions will be given later. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. Detailed implementation manners

[0054] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0055] With the development of science and technology, traditional factories are all transitioning towards big data and industrial Internet of Things, and unmanned factories have become a trend. How to transform traditional glove machine factories into unmanned factories has always been a problem we are committed to solving.

[0056] In existing glove machine factories, quality inspection is the most labor-intensive link. How to achieve unmanned quality inspection, solve missed inspections and misjudgments, reduce costs, and reduce defective products are the pain points we need to solve. For the faults of broken yarn and broken rubber elastic threads that occur during the operation of the glove machine, automated detection can be achieved, but currently, automated detection of broken needles in glove machines cannot be achieved.

[0057] In view of the above problems, the embodiments of the present application provide a method, device, storage medium, and program product for detecting broken needles in glove machines, aiming to solve the problem that automated detection of broken needles in glove machines cannot be achieved currently. The technical concept of the present application is: obtaining multiple frames of detection images through a shooting unit, determining a precise detection area through template matching initial positioning and secondary positioning, performing secondary defect image recognition processing on the determined detection area, determining the broken needle detection result of each frame of detection image, and fusing the detection results of multiple frames of images to achieve the multi-frame visual automated precise detection effect of broken needle defects in glove machines.

[0058] Figure 1 Structural diagram of a glove machine broken needle detection system provided in an embodiment of the present application, as Figure 1As shown, the broken needle detection system for a glove machine includes: a detection device, a camera unit 102, a camera bracket 105, and a camera light source 106.

[0059] As the control device of the glove machine inspection system, the inspection equipment and the main control device 101 of the glove machine can be integrated into one component, or the inspection equipment and the main control device 101 of the glove machine can be two components, with the inspection equipment embedded inside the glove machine.

[0060] The glove-making machine includes a frame 10, a needle structure 103, a thread frame 107, and a thread frame support 104. The thread frame support 104 is mounted on the frame 10, and the thread frame 107 is mounted on the thread frame support 104. The thread frame 107 supports the knitting yarn, facilitating the connection of the knitting needles to the yarn. The needle structure 103 is located at the center of the glove-making machine and is used to connect the yarn to knit the glove. The needle structure 103 includes a needle array, which refers to multiple knitting needles distributed in an array.

[0061] The imaging bracket 105 is fixed on the thread frame bracket 104 of the glove machine. The imaging unit 102 is mounted on the imaging bracket 105 and is located directly above the needle array. The imaging unit 102 is used to capture images of the needle array 103. The imaging light source 106 is fixed on the lower side of the thread frame 107 and is symmetrically distributed around the thread frame bracket 104. The imaging light source 106 is located on both sides of the imaging unit 102 and is used to assist the imaging unit 102 in capturing images. When the detection equipment is integrated with the main control device 101 of the glove machine, the detection equipment and the imaging unit 102 are connected through the peripheral interface of the main control device 101 of the glove machine.

[0062] The detection system places the imaging unit 102 and the imaging light source 106 above the needle array. During the glove-making process, the yarn frame inevitably vibrates, so a separate imaging bracket 105, perpendicular to the yarn frame support 104, is designed to work with the imaging light source 106 to stabilize the image captured by the imaging unit 102. After confirming the glove is finished knitting, the system checks if the glove has fallen. If it has, the imaging light source 106 is turned on, and the system checks if the operating head is above the needle array. If so, the operating head is moved to one side of the needle array, and the glove-making machine controls the imaging unit 102 to capture the first frame of the detection image via the detection equipment. Because the needle height differs when the operating head is on the left or right side of the machine, some needles may be obscured by the sinker plate. Therefore, the operating head needs to be moved to the other side of the needle array to capture the second frame of the detection image for image recognition and analysis, ensuring the accuracy of needle breakage detection. The glove machine inspection system begins by processing the detected images through initial template positioning and matching, and secondary positioning to determine the precise detection area. It then performs secondary defect image recognition on the determined detection area to determine the broken needle detection result of each frame of the detection image. The detection results of multiple frames are then fused to achieve multi-frame visual automated and accurate detection of broken needle defects in the glove machine.

[0063] like Figure 2 As shown, one embodiment of this application provides a method for detecting broken needles in a glove machine, the method comprising the following steps:

[0064] S101. The detection equipment acquires multiple frames of detection images during the operation of the glove machine.

[0065] In this step, the detection image includes the knitting needle structure area. Since machine vibration is unavoidable, the detection image is acquired under vibration conditions. When the glove machine finishes knitting, the sensing device detects the glove falling off and sends a command to the glove machine's detection device via CAN interface communication. The detection device parses the data and generates an image capture command, which is sent to the imaging unit via USB. The imaging unit parses and captures the detection image of the glove machine's knitting needle array, thus acquiring the detection image.

[0066] S102. For each frame of the detection image, the detection device matches the preset jitter correction template with the detection image to obtain the initial positioning position of at least one target needle tip located in the middle of the needle array.

[0067] In this step, the jitter correction template is a standard image that is stored in advance in the glove machine controller to take into account the unavoidable jitter of the machine, and is obtained by loading it upon power-on.

[0068] The jitter correction template needle array is divided into a jitter correction region and a first central region of the needle array, which have a relative positional relationship. The corresponding region that best matches the jitter correction template and the detection image is selected from the detection image for image recognition. The two are matched by grayscale values ​​and pixels to obtain the first reference region.

[0069] The second central region of the needle array in the detection image is determined based on the relative relationship and the first reference region. That is, the middle position of the needle array in the detection image is the second central region. Considering the problem of image unit distortion, the clearest and most stable position of the needle array is selected as the middle position of the needle array. Image recognition is performed on the second central region to obtain the initial positioning position of at least one target needle tip, so as to facilitate secondary positioning.

[0070] S103. For each frame of the detection image, the detection device matches the calibrated position of each needle tip with the initial positioning position of at least one target needle tip to determine the position of each needle tip in the detection image.

[0071] In this step, the calibration position of each needle tip is obtained by loading a calibration file stored in the controller of the glove machine testing equipment in advance, taking into account the unavoidable vibration of the machine.

[0072] The initial positioning position of at least one target needle tip is obtained from step S102, and a reference needle tip is selected according to the principle of intermediate position.

[0073] Secondary positioning is performed using the calibration position. The calibration position of each needle tip is matched with the position of the reference needle tip to determine the offset between the initial positioning position and the calibration position of the reference needle tip. The calibration position of each needle tip is offset according to the offset to accurately obtain the position of each needle tip in the detection image.

[0074] S104. The detection equipment performs image recognition based on the position of each needle tip to determine the broken needle detection result of each frame of detection image.

[0075] In this step, for a single frame detection image, the detection area of ​​each needle tip is determined according to the position of each needle tip, and image recognition is performed on the detection area of ​​each needle tip. The broken needle result is detected by using factors such as gray value, gradient, roundness, and area of ​​the needle tip position.

[0076] If the needle breakage detection results of each needle tip indicate no broken needles, then the needle breakage detection result of the detection image is determined to be no broken needles; if the needle breakage detection result of at least one needle tip indicates a broken needle, then the needle tip with the broken needle detection result is marked as a suspicious needle tip; then a secondary defect judgment is performed.

[0077] For each suspicious needle tip, a suspicious area is determined based on the position of the needle tips adjacent to the suspicious needle tip. Image recognition is performed on the suspicious area to prevent missed detections. If the recognition result of each suspicious area is no broken needle, the broken needle detection result of the detection image is determined to be no broken needle. If the recognition result of at least one suspicious area is a broken needle, the broken needle detection result of the detection image is determined to be a broken needle, and the broken needle position is saved for analysis.

[0078] S105. The detection equipment generates the final broken needle detection result based on the broken needle detection result of each frame of the detection image.

[0079] In this step, based on the broken needle detection result of a single frame detection image, the detection results of multiple frames are fused. When the broken needle detection results of multiple frames are all broken needles, it is determined whether the broken needle positions of the multiple frames are the same. When at least one broken needle position is the same, it is determined that there is a broken needle in the knitting needle structure. When all broken needle positions are different, it is determined that there is no broken needle in the knitting needle structure, thus preventing false alarms from the broken needle defect detection system.

[0080] In the above technical solution, multiple frames of detection images are acquired by the imaging unit, and the shake correction template and the detection images are initially matched for positioning. The calibrated position of each needle tip is matched for secondary positioning with the initial positioning position of at least one target needle tip. The position of each needle tip in the detection image is determined through two-step positioning. Then, image recognition is performed based on the position of each needle tip to determine the needle breakage detection result of each frame of detection image, solving the problems of unavoidable machine shake and missed detections and false detections. The needle breakage detection results of each frame of detection image are fused to generate the final needle breakage detection result, and the needle breakage detection result of the glove machine is determined, realizing two defect judgments and solving the problem of false alarms in the system. This improves the accuracy of the needle breakage detection result and achieves a multi-frame visual automated accurate detection effect for needle breakage defects in the glove machine.

[0081] In one embodiment, step S102 specifically includes:

[0082] S201. The detection device matches the preset jitter correction template with the detection image to obtain the first reference area in the detection image corresponding to the jitter correction area.

[0083] Among them, such as Figure 3 As shown, the jitter correction template includes a jitter correction area 202 and a first central area 201 of the needle array 205. The first central area of ​​the needle array 205 is the clearer area of ​​the needle array, and the jitter correction area 202 is the right side area of ​​the first central area 201 of the needle array.

[0084] Image recognition is performed by selecting the corresponding region that best matches the jitter correction template and the detection image from the detection image, and matching the two by grayscale value and pixel point to obtain the first reference region 203.

[0085] For example, when matching the jitter correction template with the detection image pixel by pixel, the coordinates of the center point of the jitter correction region 202 of the jitter correction template are (20, 20). The coordinates of the center point of the region in the detection image that is close to the gray value in the jitter correction region 202 are (20.5, 20.5), thereby obtaining the first reference region 204 corresponding to the jitter correction region 202.

[0086] S202. The detection device determines the second central region of the needle array in the detection image based on the relative relationship between the jitter correction area and the first central region in the jitter correction template, and the first reference region.

[0087] In this step, the relative relationship between the jitter correction region 202 and the first central region 201 in the jitter correction template is the positional relationship of their regional center points. Based on the positional relationship of the regional center points and the position of the center point of the first reference region 204, the center position of the second central region 203 is determined. Then, taking the center position of the second central region 203 as the center, the second central region 203 is determined with a preset width and length. The second central region 203 is the central region of the needle array region in the detection image.

[0088] For example, if the center point of the jitter correction area 202 is (20, 20), the center point of the first central area 201 is (10, 10), and the center point of the first reference area 204 is (19, 19), then the center point of the second central area 203 of the needle array is (9, 9). Using a preset length of 3 and a width of 2, the second central area 203 is determined. Therefore, the four corner points of the second central area 203 are (6, 7), (6, 11), (12, 7), and (12, 11).

[0089] S203. The detection equipment performs needle tip image recognition on the second central area to determine the initial positioning position of at least one target needle tip.

[0090] In this step, due to camera distortion, the central region of the area containing the knitting needle array in the detected image has the least distortion and the highest clarity. That is, the second central region 203 has little distortion and high clarity. Image recognition is performed on the second central region 203 to obtain at least one target needle tip and its position. Existing image recognition technology can be used to identify the needle tip in the second central region 203, which will not be elaborated here.

[0091] In the above technical solution, the central region of the area where the needle array is located in the detection image is determined by matching the pixels of the jitter correction template and the detection image. Then, image recognition is performed on this region, reducing the image recognition area and improving image recognition efficiency. Moreover, the pixel distortion in the central region of the area where the needle array is located is small, and image recognition in this region has a lower recognition accuracy, achieving precise initial positioning of the target needle tip and improving the accuracy of detection.

[0092] In one embodiment, step S103 specifically includes:

[0093] S301. The detection device selects a reference needle tip from at least one target needle tip based on the initial positioning position of at least one target needle tip, and determines the initial positioning position of the reference needle tip.

[0094] In one embodiment, after obtaining the initial positioning position of at least one target needle tip, the middle target needle tip is selected from the at least one target needle tip as the reference needle tip.

[0095] For example: Continue to refer to Figure 3 When there are 3 target needle tips, and the initial positioning positions of the 3 target needle tips have been obtained in step S102, the middle one is selected as the reference needle 206, and the initial positioning position of the middle needle tip is taken as the initial positioning position of the reference needle tip.

[0096] In one embodiment, after obtaining the initial positioning position of at least one target needle tip, any target needle tip is selected from the at least one target needle tip as a reference needle tip.

[0097] When there are 4 target needle tips, and the initial positioning positions of the 4 target needle tips have been obtained in step S102, any target needle tip is selected as the reference needle tip. If the second target needle tip is selected as the reference needle tip, then the initial positioning position of the second target needle tip is used as the initial positioning position of the reference needle tip.

[0098] S302. The testing equipment matches the initial positioning position of the reference needle tip with the calibrated position of each needle tip to determine the offset between the initial positioning position and the calibrated position of the reference needle tip.

[0099] In this step, the calibration positions of each needle tip are pre-stored in the testing equipment. The initial positioning position of the reference needle tip is compared with the calibration positions of each needle tip one by one. The calibration position of the needle tip closest to the initial positioning position of the reference needle tip is determined and used as the calibration position of the reference needle tip. The offset between the initial positioning position and the calibration position of the reference needle tip is calculated.

[0100] For example, the initial positioning position of the reference needle tip is (5, 5), and the calibration positions of each needle tip are (3.7, 3.7), (4.7, 4.7), (5.7, 5.7), (6.7, 6.7), and (7.7, 7.7). Find the calibration position that is closest to the initial positioning position of the reference needle tip from the calibration positions of each needle tip. (4.7, 4.7) is the calibration position of the reference needle tip. The offset between the initial positioning position and the calibration position of the reference needle tip is calculated to be (0.7, 07).

[0101] S303. The detection equipment performs overall offset processing on the calibration position of each needle tip according to the offset amount to obtain the position of each needle tip in the detection image.

[0102] In this step, for each needle tip's calibrated position, the offset is subtracted from the calibrated position to obtain the position of each needle tip, thereby obtaining the position of each needle tip in the detection image.

[0103] For example, the calibrated positions of each needle tip are (3.7, 3.7), (4.7, 4.7), (5.7, 5.7), (6.7, 6.7), and (7.7, 7.7). Subtracting the offset (0.7, 07) from the calibrated position of each needle tip, we obtain the positions of each needle tip as (3, 3), (4, 4), (5, 5), (6, 6), and (7, 7).

[0104] In the above technical solution, for a single frame detection image, a clear small area of ​​the knitting needle array is selected for image recognition, which facilitates efficient data processing; the calibrated position of each needle tip is matched more accurately with the initial positioning position of at least one target needle tip to determine the position of each needle tip in the detection image, which further improves the accuracy of detection.

[0105] In one embodiment, obtaining the calibration position of each needle tip specifically includes:

[0106] S401. The testing equipment acquires two calibration images.

[0107] In this step, the imaging unit is connected to the testing device equipped with auxiliary calibration software via USB. The auxiliary calibration software is then launched. Its interface includes controls for enabling the imaging light source, enabling the imaging unit, acquiring the first frame image, acquiring the second frame image, loading the first frame image, and loading the second frame image.

[0108] Click to activate the shooting light source control. The detection device sends a command to activate the shooting light source, which then projects light onto the knitting needle array. Click to activate the shooting unit control, powering on the shooting unit and putting it into ready state.

[0109] Because the needle-starting height differs when the operating head is on the left or right side of the glove machine, some needles may be obscured by the sinker. Therefore, one image is captured each time the operating head is on the left and right sides of the glove machine. Clicking the "Capture First Frame Image" control moves the operating head to one side of the needle array, controlling the imaging unit to capture the first frame of the glove machine's inspection image. Clicking the "Load First Frame Image" control transmits the first frame of the inspection image to the inspection device. Clicking the "Capture Second Frame Image" control moves the operating head to the other side of the needle array, controlling the imaging unit to capture the second frame of the glove machine's inspection image. Clicking the "Load Second Frame Image" control transmits the second frame of the inspection image to the inspection device.

[0110] S402. The detection equipment collects the click positions of the user on two calibration images and obtains the calibration positions of each needle tip based on the click positions.

[0111] In this step, the first frame of the detection image is displayed on the interface of the auxiliary calibration software. The user clicks on the position of each needle tip on the first calibration image one by one, and the click position of the user on the first calibration image is collected. The collected click position is used as the calibration position of the needle tip that is not blocked by the settling head in the first frame of the detection image.

[0112] The second frame of the detection image is displayed on the interface of the auxiliary calibration software. The user clicks on the position of each needle tip on the second calibration image one by one, and the click position of the user on the second calibration image is collected. The collected click position is used as the calibration position of the needle tip that is not blocked by the settling head in the second frame of the detection image.

[0113] By merging the calibration positions of the needle tips that are not obscured by the settling head in the first frame of the detection image and the calibration positions of the needle tips that are not obscured by the settling head in the second frame of the detection image, the calibration positions of each needle tip can be obtained.

[0114] S403. The detection equipment acquires the position of the marked area of ​​the operation on two calibration images, and generates a jitter correction image template based on the position of the marked area and the calibration position of each needle tip.

[0115] In this step, the first frame of the detection image is displayed on the interface of the auxiliary calibration software, and the center position of the marked area operated by the user on the first frame of the detection image is acquired. The second frame of the detection image is displayed on the interface of the auxiliary calibration software, and the center position of the marked area operated by the user on the second frame of the detection image is acquired. The average of the two center positions is taken as the center position of the jitter correction area, and the jitter correction area is determined with a preset length and width.

[0116] The center position of the needle array is determined based on the calibration position of each needle tip, and this center position is used as the center position of the first central region. The first central region is defined with a preset length and width, and the relative positional relationship between the center position of the first central region and the jitter correction region is calculated. A jitter correction image template is generated based on the relative positional relationship between the center position of the first central region and the jitter correction region, the jitter correction region, and the calibration position of each needle tip.

[0117] In the above technical solution, the calibration position of each needle tip is determined directly by the precise calibration method of the calibration software, and a shake correction image template is generated, which solves the problem of image unit distortion and improves the accuracy of detection.

[0118] In one embodiment, such as Figure 4 As shown, step S104 specifically includes:

[0119] S501. For each frame of the detection image, the detection equipment determines the detection area of ​​each needle tip based on the position of each needle tip, and performs image recognition on the detection area of ​​each needle tip to determine the broken needle detection result of each needle tip.

[0120] In this step, in order to achieve more accurate and efficient image recognition, for each frame of the detection image, the detection area of ​​each needle tip is first determined according to the position of each needle tip. The image recognition of the precise detection area of ​​each needle tip is performed using factors such as gray value, gradient, roundness, and area of ​​the needle tip position, so as to obtain the result of needle tip breakage detection.

[0121] More specifically, the grayscale value of the needle tip position is used to determine whether the needle breakage detection results of each needle tip indicate that there is no broken needle. For example, if the grayscale value of each needle tip is lower than a certain value, the needle tip is determined to be broken.

[0122] S502. The detection equipment determines whether the needle breakage detection results of each needle tip indicate no needle breakage. If yes, proceed to S503; otherwise, proceed to S504.

[0123] In this step, to increase the accuracy of needle breakage detection, it is determined whether the needle breakage detection results of all needle tips indicate no needle breakage. If the needle breakage detection results of all needle tips indicate no needle breakage, then the needle breakage detection result of the detection image is determined to be no needle breakage, and the process ends.

[0124] For example: If, in a detection area containing 10 needle tips in a certain frame of a detection image, image recognition determines that the detection result of broken needles for all 10 needle tips is that there are no broken needles, then the detection result of broken needles in that frame of the detection image is determined to be that there are no broken needles.

[0125] S503. If the needle breakage detection results of each needle tip indicate no broken needles, then the needle breakage detection result of the detection image is determined to be no broken needles, and the process ends.

[0126] In this step, to prevent missed detections, the detection result of the broken needle in the detection image is determined to be without broken needles only when the broken needle detection results of each needle tip indicate that there are no broken needles, and the process ends, completing the detection of broken needle results for a single frame detection image.

[0127] S504. If the detection equipment detects a broken needle at least once, the needle tip with the broken needle detection result is marked as a suspicious needle tip.

[0128] In this step, the unavoidable vibration of the machine is taken into account to prevent false detections. If the detection result of at least one needle tip in the detection area is a broken needle, the needle tip with the broken needle detection result is initially identified as a suspicious needle tip.

[0129] For example: By detecting a detection area with 10 needle tips in a certain frame of detection image, the image recognition determines that the needle breakage detection results of the 1st to 9th needle tips are all without needle breakage, while the needle breakage detection result of the 10th needle tip is that there is a needle breakage. The 10th needle tip is then regarded as a viable needle tip.

[0130] S505. For each suspicious needle tip, the detection equipment determines the suspicious area based on the position of the needle tips adjacent to the suspicious needle tip, and performs image recognition on the suspicious area.

[0131] In this step, each suspicious needle tip is further analyzed, and the center position of the suspicious area is calculated based on the positions of the two needle tips on either side of the suspicious needle tip. In one embodiment, the two needle tips on either side of the selected suspicious needle tip are symmetrical about the center of the suspicious needle tip, and the center position of the suspicious area is obtained by calculating the average position of the two needle tips on either side of the suspicious needle tip.

[0132] Image recognition is performed on suspicious areas using factors such as the gray value, gradient, roundness, and area of ​​the needle tip to obtain image recognition results for the suspected areas. For example, when the gray value is below a certain value, the needle tip is determined to be a broken needle, and when the gray value is above a certain value, the needle tip is determined to be a intact needle.

[0133] S506. The detection equipment determines whether the identification result of each suspicious area is that there are no broken needles. If so, proceed to S507; otherwise, proceed to S508.

[0134] S507. If the identification result of each suspicious area is no broken needle, then the broken needle detection result of the detection image is determined to be no broken needle.

[0135] In this step, the unavoidable jitter of the machine is taken into account. Only when the recognition result of each suspicious area is no broken needle is the broken needle detection result of the detection image determined to be no broken needle, thus solving the false alarm problem of broken needle detection in the system.

[0136] S508. If the detection device identifies a broken needle in at least one suspicious area, it determines that the broken needle detection result of the detection image is a broken needle and stores the broken needle location.

[0137] In this step, a second defect judgment is performed. If the identification result of at least one suspicious area is still that there is a broken needle, then the broken needle detection result of the detection image is determined to be that there is a broken needle, and the broken needle location is stored in the detection device for easy analysis.

[0138] In the above technical solution, for a single-frame detection image, two defect image recognition judgments are performed to solve the problems of unavoidable machine jitter and missed detections and false detections, prevent false alarms from occurring in the detection system, and improve the accuracy of needle breakage detection results for single-frame images.

[0139] like Figure 5 As shown, one embodiment of this application provides a method for detecting broken needles in a glove machine, the method comprising the following steps:

[0140] S601. The detection equipment acquires two frames of detection images when the glove machine is in operation.

[0141] In this step, when the glove machine finishes knitting, the sensing device detects the glove falling off and sends a command to the glove machine's detection device via CAN interface communication. The detection device parses the data and generates a shooting command, which is sent to the shooting unit via USB. The shooting unit parses the command and captures a detection image of the glove machine's knitting needle array when the operating head is located on both sides of the pointer array, thereby obtaining the detection image.

[0142] In one embodiment, such as Figure 6 As shown, two frames of detection images are obtained when the glove machine is in operation, specifically including:

[0143] S701. After confirming that the glove is finished knitting, the detection equipment checks whether the glove has fallen. If yes, proceed to S702; otherwise, continue to S701.

[0144] In this step, the glove knitting is completed by the detection equipment inside the glove machine, and the glove is detected by the sensor equipment to see if it has fallen off. When the sensor equipment detects that the glove has fallen off, it sends a signal to the glove machine through the interface.

[0145] S702. If the glove falls, the detection device generates the first activation command.

[0146] In this step, when the sensor device detects that the glove has fallen off, it sends a signal to the glove machine via an interface. The glove machine's detection device then generates a first activation command. This first activation command is used to turn on the light source. The glove machine's detection device defines the first activation command as turning on the light source through software and sends it to the imaging light source, so that the imaging light source provides light for the imaging unit to capture images.

[0147] S703. The detection device checks whether the operating head is above the needle array. If yes, proceed to S704; otherwise, proceed to S705.

[0148] In this step, the glove machine operating head is used to operate the knitting of the glove. The sensor detects whether the operating head is above the knitting needle array. When the operating head is above the knitting needle array, it will affect the imaging unit's ability to take pictures of the knitting needle array. Therefore, it is necessary to first detect whether the operating head is above the knitting needle array through the sensor.

[0149] S704, The detection equipment generates a second movement command.

[0150] In this step, the second movement command is used to control the operating head to move to one side of the needle array. The second movement command is generated by the controller running the method program; when the operating head is detected to be above the needle array, the controller generates the second movement command through program execution, sends the command to the operating head, the operating head parses the command, interacts with the detection system, and moves to one side of the needle array. In the glove machine inspection equipment, the second movement command is defined by software as the operating head moving to one side of the needle array.

[0151] S705, the detection equipment generates the first shooting command.

[0152] The first shooting command is used to control the camera to capture the first frame of the glove machine's detection image;

[0153] In this step, the operating head is not above the knitting needle array. The controller generates a first shooting command through program execution. The first shooting command, defined by software, controls the camera to capture the first frame of the glove machine's inspection image.

[0154] The controller sends the first shooting command to the camera, which then takes a picture upon receiving the command. More specifically, the controller sends the first shooting command to the imaging unit via a USB port. Upon receiving the command, the imaging unit parses it, takes a picture, and acquires the first detection image.

[0155] S706, The detection equipment generates a third movement command.

[0156] In this step, the third movement command is used to control the operating head to move to the other side of the needle array. Since the needle height is different when the operating head is on the left and right sides of the machine, some needles may be blocked by the sinker. Therefore, the operating head takes one picture on the left and one on the right side of the machine for image recognition and analysis to ensure the accuracy of the broken needle detection results. When the operating head moves to one side of the needle array and takes a picture, the controller generates the third movement command through the program and sends the third command to the control operating head. The operating head parses the command, interacts with the detection system, and moves to the other side of the needle array.

[0157] S707, The detection equipment generates a second shooting command.

[0158] In this step, the controller generates a second shooting command through program execution and sends it to the shooting unit via USB port. Upon receiving the shooting command, the shooting unit parses it, takes a picture, and acquires the second detection image. The glove machine inspection equipment uses software to define the second shooting command to capture a second frame of the glove machine's inspection image using the camera.

[0159] S602. For each frame of the detection image, the detection device matches the preset jitter correction template with the detection image to obtain the initial positioning position of at least one target needle tip located in the middle of the needle array.

[0160] S603. For each frame of the detection image, the detection device matches the calibrated position of each needle tip with the initial positioning position of at least one target needle tip to determine the position of each needle tip in the detection image.

[0161] S602 has been described in detail in S102, and S603 has been described in detail in S103, so it will not be repeated here.

[0162] S604. The detection equipment performs image recognition based on the position of each needle tip to determine the broken needle detection result of each frame of detection image.

[0163] This step has already been explained in detail in S104, and will not be repeated here.

[0164] S605. The detection device determines whether the final broken needle detection result of the first frame detection image is that there is a broken needle. If yes, proceed to S606; otherwise, proceed to S609.

[0165] S606. The detection device determines that the final broken needle detection result of the second frame detection image is that there is a broken needle. If so, proceed to S607; otherwise, proceed to S609.

[0166] In this step, considering the unavoidable machine jitter, based on the final broken needle detection result of the first frame detection image, it is then determined whether the final broken needle detection result of the second frame detection image also indicates a broken needle, thus resolving the issue of false alarms. If the final broken needle detection result of the second frame detection image indicates a broken needle, to prevent false alarms, it is further determined whether the broken needle position in the first frame detection image is the same as the broken needle position in the second frame detection image. If they are the same, it is confirmed that a broken needle exists.

[0167] S607. The detection device determines whether the broken needle position in the first frame of the detection image is the same as the broken needle position in the second frame of the detection image. If yes, proceed to S608; otherwise, proceed to S609.

[0168] In this step, the broken needle position in the first frame detection image is compared with the broken needle position in the second frame detection image to determine whether the broken needle positions in the first and second frames are the same. If the broken needle positions in the first and second frames are the same, it is determined that a broken needle exists in the knitting needle structure; if the broken needle positions in the first and second frames are different, it is determined that no broken needle exists in the knitting needle structure.

[0169] For example: There are 3 broken needle positions in the first frame detection image and 2 broken needle positions in the second frame detection image. Compare the 3 broken needle positions in the first frame detection image with the 2 broken needle positions in the second frame detection image. If the broken needle positions in the first frame detection image and the broken needle positions in the second frame detection image are not the same, then it is determined that there are no broken needles in the needle array.

[0170] If the first broken needle position in the first frame of the detection image is the same as the first broken needle position in the second frame of the detection image, then it is determined that there is a broken needle in the needle array, and the broken needle position is the first broken needle position in the first frame of the detection image.

[0171] S608. The testing equipment determined that there were broken needles in the knitting needle structure.

[0172] In this step, if the broken needle position in the first frame detection image is the same as the broken needle position in the second frame detection image, it is determined that there is a broken needle in the knitting needle structure.

[0173] S609. The testing equipment confirms that there are no broken needles in the knitting needle structure.

[0174] In this step, if the broken needle position in the first frame detection image is different from the broken needle position in the second frame detection image, it is determined that there is no broken needle in the knitting needle structure.

[0175] S610. When the detection equipment determines that there is a broken needle in the knitting needle structure, it sends a broken needle alarm message to the main control equipment.

[0176] In this step, the controller determines that there is a broken needle in the knitting needle structure through the above analysis, and sends the broken needle alarm signal to the main control device through the peripheral interface.

[0177] In the above technical solution, when the final broken needle detection result of the first frame detection image is that there is a broken needle, to prevent the system from falsely reporting, the final broken needle detection result of the second frame detection image is then determined to be that there is a broken needle. If the final broken needle detection result of the second frame detection image is that there is a broken needle, the broken needle position is further determined to be the same. If they are the same, it is determined that there is a broken needle. This solves the unavoidable jitter problem and the problem of false detection and missed detection of the machine, prevents the system from falsely reporting, and realizes multi-frame visual automated accurate detection of broken needle defects in glove machines.

[0178] like Figure 7 As shown, one embodiment of this application provides a broken needle detection device 800 for a glove machine, the device comprising:

[0179] The acquisition module 801 is used to acquire multiple frames of detection images during the operation of the glove machine, wherein the detection images include the knitting needle structure area;

[0180] The processing module 802 is used to match the preset jitter correction template with the detection image for each frame of the detection image to obtain the initial positioning position of at least one target needle tip located in the middle of the needle array.

[0181] The processing module 802 is also used to match the calibrated position of each needle tip with the initial positioning position of at least one target needle tip for each frame of the detection image, so as to determine the position of each needle tip in the detection image.

[0182] The processing module 802 is also used to perform image recognition based on the position of each needle tip, determine the broken needle detection result of each frame of detection image, and generate the final broken needle detection result based on the broken needle detection result of each frame of detection image.

[0183] In one embodiment, the processing module 802 is specifically used for:

[0184] The preset jitter correction template is matched with the detection image to obtain the first reference region in the detection image corresponding to the jitter correction region; wherein, the jitter correction template includes the jitter correction region and the first central region of the knitting needle array;

[0185] The second central region of the needle array in the detection image is determined based on the relative relationship between the jitter correction region and the first central region in the jitter correction template, and the first reference region.

[0186] The second central region is used for needle tip image recognition to determine the initial positioning position of at least one target needle tip.

[0187] In one embodiment, the processing module 802 is specifically used for:

[0188] A reference needle tip is selected from at least one target needle tip based on the initial positioning position of at least one target needle tip, and the initial positioning position of the reference needle tip is determined.

[0189] Match the initial positioning position of the reference needle tip with the calibrated position of each needle tip to determine the offset between the initial positioning position and the calibrated position of the reference needle tip.

[0190] The calibration positions of each needle tip are offset as a whole based on the offset amount to obtain the position of each needle tip in the detection image.

[0191] In one embodiment, the processing module 802 is specifically used for:

[0192] For each frame of the detection image, the detection area of ​​each needle tip is determined according to the position of each needle tip, and image recognition is performed on the detection area of ​​each needle tip to determine the broken needle detection result of each needle tip.

[0193] If the needle breakage detection results for each needle tip indicate no broken needles, then the needle breakage detection result for the detection image is determined to be no broken needles.

[0194] In one embodiment, the processing module 802 is specifically used for:

[0195] If the needle breakage detection result of at least one needle tip is a broken needle, then the needle tip with the broken needle detection result is marked as a suspicious needle tip;

[0196] For each suspicious needle tip, the suspicious area is determined based on the position of the needle tips adjacent to the suspicious needle tip, and image recognition is performed on the suspicious area;

[0197] If the identification result of each suspicious area is no broken needle, then the broken needle detection result of the detection image is determined to be no broken needle;

[0198] If the identification result of at least one suspicious area is that there is a broken needle, then the broken needle detection result of the detection image is determined to be that there is a broken needle, and the broken needle location is stored.

[0199] In one embodiment, the acquisition module 802 is specifically used for:

[0200] When it is determined that the operating head is directly above the needle array, a first movement command is generated. The first movement command is used to control the operating head to move to one side of the needle array.

[0201] Generate a first shooting command, wherein the first shooting command controls the camera to capture the first frame of the glove machine's detection image;

[0202] A second movement command is generated, which controls the operating head to move to the other side of the needle array;

[0203] Generate a second shooting command, wherein the second shooting command controls the camera to capture a second frame of the glove machine's detection image;

[0204] or

[0205] When it is determined that the operating head is located on one side of the needle array, a first shooting command is generated, which controls the camera to capture the first frame of the glove machine's detection image;

[0206] Generate a second movement command, the first movement command being used to control the operating head to move to the other side of the needle array;

[0207] A second shooting command is generated, wherein the second shooting command controls the camera to capture a second frame of the glove machine's detection image.

[0208] In one embodiment, the processing module 802 is specifically used for:

[0209] When both the final broken needle detection result of the first frame detection image and the final broken needle detection result of the second frame detection image show broken needles, determine whether the broken needle position of the first frame detection image and the broken needle position of the second frame detection image are the same.

[0210] If at least one broken needle is in the same location, the knitting needle structure is determined to have a broken needle; if all broken needles are in different locations, the knitting needle structure is determined not to have a broken needle.

[0211] like Figure 8 As shown, one embodiment of this application provides a detection device 900, which includes a memory 901 and a processor 902.

[0212] Among them, memory 901 is used to store computer instructions that can be executed by the processor;

[0213] The processor 902 implements the various steps of the method in the above embodiments when executing computer instructions. For details, please refer to the relevant descriptions in the foregoing method embodiments.

[0214] Optionally, the memory 901 can be either independent or integrated with the processor 902. When the memory 901 is configured independently, the detection device also includes a bus for connecting the memory 901 and the processor 902.

[0215] This application also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the steps of the methods described above.

[0216] This application also provides a computer program product, including computer instructions that, when executed by a processor, implement the various steps in the methods described above.

[0217] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0218] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for detecting broken needles in a glove machine, characterized in that, The glove machine is equipped with a knitting needle structure, the knitting needle structure including a knitting needle array, and the method includes: Acquire multiple frames of detection images during the operation of the glove machine, wherein the detection images include the knitting needle structure region; For each frame of the detection image, a preset jitter correction template is matched with the detection image to obtain the initial positioning position of at least one target needle tip located in the middle of the needle array. For each frame of the detection image, the calibrated position of each needle tip is matched with the initial positioning position of at least one target needle tip to determine the position of each needle tip in the detection image. Image recognition is performed based on the position of each needle tip to determine the needle breakage detection result for each frame of the detection image; the final needle breakage detection result is generated based on the needle breakage detection result for each frame of the detection image. The step of matching the preset jitter correction template with the detection image to obtain the initial positioning position of at least one target needle tip located in the middle of each row of needle tips specifically includes: The preset jitter correction template is matched with the detection image to obtain a first reference region in the detection image corresponding to the jitter correction region; wherein, the jitter correction template includes the jitter correction region and a first central region of the knitting needle array; The second central region of the needle array in the detection image is determined based on the relative relationship between the jitter correction region and the first central region in the jitter correction template, and the first reference region. The second central region is subjected to needle tip image recognition to determine the initial positioning position of at least one target needle tip.

2. The method according to claim 1, characterized in that, For each frame of the detection image, the calibrated position of each needle tip is matched with the initial positioning position of at least one target needle tip to determine the position of each needle tip in the detection image, specifically including: A reference needle tip is selected from the at least one target needle tip based on the initial positioning position of the at least one target needle tip, and the initial positioning position of the reference needle tip is determined. The initial positioning position of the reference needle tip is matched with the calibrated position of each needle tip to determine the offset between the initial positioning position and the calibrated position of the reference needle tip. The calibration positions of each needle tip are offset as a whole based on the offset amount to obtain the position of each needle tip in the detection image.

3. The method according to claim 1, characterized in that, Based on the position of each needle tip, image recognition is performed to determine the broken needle detection result for each frame of the detection image, specifically including: For each frame of the detection image, the detection area of ​​each needle tip is determined according to the position of each needle tip, and image recognition is performed on the detection area of ​​each needle tip to determine the broken needle detection result of each needle tip. If the needle breakage detection results of each needle tip indicate no broken needles, then the needle breakage detection result of the detection image is determined to be no broken needles.

4. The method according to claim 3, characterized in that, Based on the position of each needle tip, image recognition is performed to determine the broken needle detection result for each frame of the detection image, which also includes: If the needle breakage detection result of at least one needle tip is a broken needle, then the needle tip with the broken needle detection result is marked as a suspicious needle tip; For each suspicious needle tip, a suspicious region is determined based on the position of the needle tips adjacent to the suspicious needle tip, and image recognition is performed on the suspicious region; If the identification result of each suspicious area is no broken needle, then the broken needle detection result of the detection image is determined to be no broken needle; If the identification result of at least one suspicious area is that there is a broken needle, then the broken needle detection result of the detection image is determined to be that there is a broken needle, and the broken needle location is stored.

5. The method according to claim 1, characterized in that, Acquiring multiple frames of detection images during the operation of the glove machine specifically includes: When it is determined that the operating head is directly above the needle array, a first movement command is generated. The first movement command is used to control the operating head to move to one side of the needle array. Generate a first shooting instruction, wherein the first shooting instruction controls the camera to capture a first frame of the detection image of the glove machine; A second movement command is generated, which controls the operating head to move to the other side of the needle array; Generate a second shooting command, wherein the second shooting command controls the camera to capture a second frame of the detection image of the glove machine; or When it is determined that the operating head is located on one side of the knitting needle array, a first shooting command is generated, which controls the camera to capture the first frame of the detection image of the glove machine; A second movement command is generated, wherein the first movement command is used to control the operating head to move to the other side of the needle array; A second shooting command is generated, wherein the second shooting command controls the camera to capture a second frame of the detection image of the glove machine.

6. The method according to claim 5, characterized in that, The final broken needle detection result is generated based on the broken needle detection result of each frame of the detected image, specifically including: When both the final broken needle detection result of the first frame detection image and the final broken needle detection result of the second frame detection image show a broken needle, determine whether the broken needle position of the first frame detection image and the broken needle position of the second frame detection image are the same. If at least one broken needle is in the same location, it is determined that the knitting needle structure has a broken needle; if all broken needles are in different locations, it is determined that the knitting needle structure does not have a broken needle.

7. A testing device, comprising: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 6.

9. A computer program product comprising a computer program that, when executed by a processor, implements the method of any one of claims 1-6.

Images